agentleFS
IgorGanapolskyIgorGanapolsky/mac-yolo-safeguards/.agents/skills/confidence-offer-gate/SKILL.md

confidence-offer-gate

Skill3 starsChanged 4 days agoMITView on GitHub

Keep the Mac YOLO Safeguards listing when Spotify Confidence or the Confidence Agent onboarding email is the source. One buyer URL is not an experiment. Demo rows and vendor onboarding emails are not sales. Review before you act; do not install the Confidence MCP/Slack bot or call Confidence.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use when a request points at https://app.confidence.spotify.com/experiments or ~/Downloads/confidence.pdf (Meet the Confidence Agent, …

    line 8
  2. Distinctive:

    Add Slack to a shared product or launch channel, not just DMs.

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Confidence offer gate

Use when a request points at https://app.confidence.spotify.com/experiments or ~/Downloads/confidence.pdf (Meet the Confidence Agent, wherever you work) and the goal is money for Mac YOLO Safeguards.

The signed-in page on 2026-11-03 was workspace ThumbGate Workspace, plan Free, profile Igor G.. Six rows were visible. Five were marked Demo data, including Reduce checkout time (Ship). The other row was ThumbGate Direct Checkout A/B. The Mac app was not in the list.

The Confidence Agent onboarding email on 2026-11-08 (from confidence.spotify.com) pitches the Confidence Agent across Confidence Projects, Slack (Admin → Integrations → Slack → Add to Slack), MCP (claude mcp add --transport http confidence-flags https://mcp.confidence.dev/mcp/flags), and connected GitHub. Its best practices are:

  1. Give it a clear outcome: "Summarise the checkout test and flag any guardrail regressions."
  2. Add Slack to a shared product or launch channel, not just DMs.
  3. Review before you act. Treat it like a sharp teammate, not autopilot.

Confidence's own result labels are Ship, Continue, End, and Abort. Ship means a success metric improved and the guardrails held. This check uses a paid order from someone other than the founder as that success metric, keeps the project context and checkout summary local, requires human review before acting (autopilot=false), and refuses adding the remote Confidence MCP, Slack bot, or GitHub integration.

The live listing stays https://iganapolsky.gumroad.com/l/nllmvb. This check does not rewrite it, does not launch an experiment, and does not call Confidence.

node tests/test-confidence-offer-gate.js
node tools/confidence-offer-gate.js offer
node tools/confidence-offer-gate.js summary
node tools/confidence-offer-gate.js project

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.